# Context-Constrained Transfer Learning for Tabular Foundation Models via Data Distillation

arXiv: https://arxiv.org/abs/2607.04809 · HTML: https://mlsanity.com/paper/2607.04809/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 15 references that are in the map.
- First posted on arXiv 6 Jul 2026.

## Builds on (most cited first, 10 of 10)

- [Computational Optimal Transport](https://mlsanity.com/paper/1803.00567/) (2018)
- [TabICL: A Tabular Foundation Model for In-Context Learning on Large Data](https://mlsanity.com/paper/2502.05564/) (2025)
- [TabPFN-2.5: Advancing the State of the Art in Tabular Foundation Models](https://mlsanity.com/paper/2511.08667/) (2025)
- [TabDPT: Scaling Tabular Foundation Models on Real Data](https://mlsanity.com/paper/2410.18164/) (2024)
- [Transfer Learning for High-dimensional Linear Regression: Prediction, Estimation, and Minimax Optimality](https://mlsanity.com/paper/2006.10593/) (2020)
- [Transfer Learning under High-dimensional Generalized Linear Models](https://mlsanity.com/paper/2105.14328/) (2021)
- [Retrieval & Fine-Tuning for In-Context Tabular Models](https://mlsanity.com/paper/2406.05207/) (2024)
- [A Closer Look at TabPFN v2: Understanding Its Strengths and Extending Its Capabilities](https://mlsanity.com/paper/2502.17361/) (2025)
- [Drift-Resilient TabPFN: In-Context Learning Temporal Distribution Shifts on Tabular Data](https://mlsanity.com/paper/2411.10634/) (2024)
- [On Learning Representations for Tabular Data Distillation](https://mlsanity.com/paper/2501.13905/) (2025)

## Built on by (most cited first, 1 of 1)

- [GEAR: Generative Expansion and Real Anchoring for Two-Stage Distillation of Tabular Foundation Models](https://mlsanity.com/paper/2608.18849/) (2026)

## Abstract (arXiv)

Tabular Foundation Models (TFMs) have demonstrated strong empirical performance as black-box inference engines through in-context learning. However, their use in transfer learning is limited by two obstacles: strict context-size constraints and sensitivity to distribution shifts between source and target tasks. Directly pooling heterogeneous source data can therefore lead to negative transfer. To address these challenges, we propose Context-Constrained Transfer Learning via ANchoring and DIstillation (TL-ANDI), a posterior-aware distillation framework for TFMs. TL-ANDI constructs a compact source context by solving a budget-constrained optimal transport problem whose cost jointly measures target covariate coverage and posterior compatibility. The selected anchor samples are then equipped with locally distilled labels and combined with a residual calibration step using target data.